CN109063688A - LED status recognition methods based on intelligent inspection robot - Google Patents
LED status recognition methods based on intelligent inspection robot Download PDFInfo
- Publication number
- CN109063688A CN109063688A CN201810999703.8A CN201810999703A CN109063688A CN 109063688 A CN109063688 A CN 109063688A CN 201810999703 A CN201810999703 A CN 201810999703A CN 109063688 A CN109063688 A CN 109063688A
- Authority
- CN
- China
- Prior art keywords
- indicator light
- led status
- similarity
- color histogram
- inspection robot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The LED status recognition methods based on intelligent inspection robot that the invention discloses a kind of, including constructing indicator light template library, the video stream data of indicator light identification region is obtained using camera, the position of indicator light in the picture is obtained using detection algorithm, calculate the color histogram of the indicator light, the similarity that the indicator light Yu indicator light template library are calculated separately using similarity measurements quantity algorithm selects recognition result of the maximum LED status of similarity as the indicator light.The present invention replaces human eye using video camera, and computer generation carries out the processing judgement of information for people, overcomes the problems such as traditional artificial indicator light monitoring efficiency is low and manpower expends, effective to improve monitoring efficiency and accuracy rate, while also mitigating the burden of monitoring personnel.
Description
Technical field
The invention belongs to Industrial Robot Technology fields, and in particular to a kind of indicator light shape based on intelligent inspection robot
State recognition methods.
Background technique
There is a large amount of indicator lights in industrial environment, for judging whether each equipment works normally.Work as indicator light
When there is certain state, show faulty staff to be needed to handle in time.Therefore just need to monitor in real time indicator light
State, and long-term monitoring is carried out in traditional artificial monitoring is that one heavy and a hard row to hoe, when indicator light is more
Manually it can not almost accomplish to monitor comprehensively and accurately, while abnormal conditions occur after all is minority, monitoring artificial in this way will
Cause huge manpower waste and inefficiency.For the industrial scale lamp condition monitoring of traditional sense, people is not only expended
It power and is failed to report since the carelessness of monitoring personnel can easily cause, the inefficiency of monitoring.
Summary of the invention
Goal of the invention of the invention is: in order to solve problem above existing in the prior art, the invention proposes one kind
LED status recognition methods based on intelligent inspection robot.
The technical scheme is that a kind of LED status recognition methods based on intelligent inspection robot, including with
Lower step:
A, each state sample of indicator light is extracted, the color histogram of each state is calculated, constructs indicator light template respectively
Library；
B, the video stream data of indicator light identification region is obtained using the camera of intelligent inspection robot；
C, single-frame images is extracted from the video stream data that step B is obtained, indicator light is obtained in image using detection algorithm
In position；
D, the indicator light data obtained according to step C, calculate the color histogram of the indicator light；
E, the color histogram and step A that the indicator light that step D is obtained is calculated separately using similarity measurements quantity algorithm are obtained
Indicator light template library in each state color histogram similarity, select the maximum LED status of similarity as should
The recognition result of indicator light.
Further, when calculating the color histogram of indicator light, it is higher than edge using kernel function setting center pixel weight
Pixel weight.
The beneficial effects of the present invention are: the present invention passes through building LED status template library, by LED status to be identified
Similarity measurement is carried out by the way of color histogram with the sample in template library respectively, replaces human eye, meter using video camera
Calculation machine replace people carry out information processing judgement, overcome traditional artificial indicator light monitoring efficiency lowly and manpower consuming etc. ask
Topic, it is effective to improve monitoring efficiency and accuracy rate, while also mitigating the burden of monitoring personnel.
Detailed description of the invention
Fig. 1 is the flow diagram of the LED status recognition methods of the invention based on intelligent inspection robot.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, the process for the LED status recognition methods of the invention based on intelligent inspection robot is illustrated
Figure.A kind of LED status recognition methods based on intelligent inspection robot, comprising the following steps:
A, each state sample of indicator light is extracted, the color histogram of each state is calculated, constructs indicator light template respectively
Library；
B, the video stream data of indicator light identification region is obtained using the camera of intelligent inspection robot；
C, single-frame images is extracted from the video stream data that step B is obtained, indicator light is obtained in image using detection algorithm
In position；
D, the indicator light data obtained according to step C, calculate the color histogram of the indicator light；
E, the color histogram and step A that the indicator light that step D is obtained is calculated separately using similarity measurements quantity algorithm are obtained
Indicator light template library in each state color histogram similarity, select the maximum LED status of similarity as should
The recognition result of indicator light.
In an alternate embodiment of the present invention where, above-mentioned steps A first with intelligent inspection robot high-definition camera
Head obtains the image data sample of each state in indicator light target area, then calculate separately indicator light each state color it is straight
Fang Tu, to construct the template library of each state of indicator light.The present invention carries out identification judgement to each state of indicator light, can be with
Recognition efficiency and accuracy rate are increased substantially, while also reducing human cost.
The present invention is higher than edge picture when calculating the color histogram of indicator light, using kernel function setting center pixel weight
Plain weight, i.e. center pixel assign higher weight, and edge pixel assigns lower weight, to improve model accuracy.
In an alternate embodiment of the present invention where, above-mentioned steps B is obtained using the high-definition camera of intelligent inspection robot
The image data of each state of indicator light identification region is taken to get the image data of LED status to be identified is arrived.
In an alternate embodiment of the present invention where, above-mentioned steps C is extracted from the video stream data that step B is obtained includes
The single-frame images of LED status obtains the position of indicator light in the picture using detection algorithm to get LED status is arrived
Sharp picture data.
In an alternate embodiment of the present invention where, above-mentioned steps D is according to the accurate figure of the obtained LED status of step C
As data, the color histogram of the LED status is calculated.
In an alternate embodiment of the present invention where, above-mentioned steps E calculates separately step D using similarity measurements quantity algorithm and obtains
To LED status the indicator light template library that is obtained with step A of color histogram in each state color histogram phase
Like degree, recognition result of the maximum LED status of similarity as the indicator light is selected.Here similarity measurements quantity algorithm is adopted
It takes but is not limited to Pasteur's coefficient.
The present invention carries out industrial scale lamp state recognition using computer vision technique, replaces human eye, meter using video camera
Calculation machine replace people carry out information processing judgement, overcome traditional artificial indicator light monitoring efficiency lowly and manpower consuming etc. ask
Topic, it is effective to improve monitoring efficiency and accuracy rate, while also mitigating the burden of monitoring personnel.
Those of ordinary skill in the art will understand that the embodiments described herein, which is to help reader, understands this hair
Bright principle, it should be understood that protection scope of the present invention is not limited to such specific embodiments and embodiments.This field
Those of ordinary skill disclosed the technical disclosures can make according to the present invention and various not depart from the other each of essence of the invention
The specific variations and combinations of kind, these variations and combinations are still within the scope of the present invention.
Claims (2)
1. a kind of LED status recognition methods based on intelligent inspection robot, which comprises the following steps:
A, each state sample of indicator light is extracted, the color histogram of each state is calculated, constructs indicator light template library respectively；
B, the video stream data of indicator light identification region is obtained using the camera of intelligent inspection robot；
C, single-frame images is extracted from the video stream data that step B is obtained, in the picture using detection algorithm acquisition indicator light
Position；
D, the indicator light data obtained according to step C, calculate the color histogram of the indicator light；
E, the color histogram for the indicator light that step D is obtained is calculated separately using similarity measurements quantity algorithm and finger that step A is obtained
The similarity for showing the color histogram of each state in lamp template library selects the maximum LED status of similarity as the instruction
The recognition result of lamp.
2. the LED status recognition methods based on intelligent inspection robot as described in claim 1, which is characterized in that calculate
When the color histogram of indicator light, it is higher than edge pixel weight using kernel function setting center pixel weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810999703.8A CN109063688A (en) | 2018-08-30 | 2018-08-30 | LED status recognition methods based on intelligent inspection robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810999703.8A CN109063688A (en) | 2018-08-30 | 2018-08-30 | LED status recognition methods based on intelligent inspection robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109063688A true CN109063688A (en) | 2018-12-21 |
Family
ID=64757968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810999703.8A Pending CN109063688A (en) | 2018-08-30 | 2018-08-30 | LED status recognition methods based on intelligent inspection robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063688A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112215106A (en) * | 2020-09-29 | 2021-01-12 | 国网上海市电力公司 | Instrument color state identification method for transformer substation unmanned inspection system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927507A (en) * | 2013-01-12 | 2014-07-16 | 山东鲁能智能技术有限公司 | Improved multi-instrument reading identification method of transformer station inspection robot |
| CN107423719A (en) * | 2017-08-03 | 2017-12-01 | 上海物联网有限公司 | A kind of railway goods yard based on video image protects famous detection method |
| CN107553489A (en) * | 2017-09-07 | 2018-01-09 | 信帧机器人技术（北京）有限公司 | A kind of intelligent inspection robot system based on video |
| CN107705321A (en) * | 2016-08-05 | 2018-02-16 | 南京理工大学 | Moving object detection and tracking method based on embedded system |
-
2018
- 2018-08-30 CN CN201810999703.8A patent/CN109063688A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927507A (en) * | 2013-01-12 | 2014-07-16 | 山东鲁能智能技术有限公司 | Improved multi-instrument reading identification method of transformer station inspection robot |
| CN107705321A (en) * | 2016-08-05 | 2018-02-16 | 南京理工大学 | Moving object detection and tracking method based on embedded system |
| CN107423719A (en) * | 2017-08-03 | 2017-12-01 | 上海物联网有限公司 | A kind of railway goods yard based on video image protects famous detection method |
| CN107553489A (en) * | 2017-09-07 | 2018-01-09 | 信帧机器人技术（北京）有限公司 | A kind of intelligent inspection robot system based on video |
Non-Patent Citations (1)
| Title |
|---|
| 疏义桂: "基于机器视觉的铝塑泡罩包装药品缺陷检测", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112215106A (en) * | 2020-09-29 | 2021-01-12 | 国网上海市电力公司 | Instrument color state identification method for transformer substation unmanned inspection system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112380952B (en) | Power equipment infrared image real-time detection and identification method based on artificial intelligence | |
| US10410346B2 (en) | Detecting tooth wear using intra-oral 3D scans | |
| CN111242123B (en) | Power equipment fault diagnosis method based on infrared image | |
| CN101563710B (en) | Method and apparatus for identifying properties of an object detected by a video surveillance camera | |
| CN108596221B (en) | Image recognition method and device for scale reading | |
| CN110910350B (en) | Nut loosening detection method for wind power tower cylinder | |
| CN108537154A (en) | Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning | |
| CN101957325A (en) | Substation equipment appearance abnormality recognition method based on substation inspection robot | |
| CN110991360B (en) | Robot inspection point position intelligent configuration method based on visual algorithm | |
| CN103090792A (en) | Method and device which are based on machine vision and used for automatic and separate detection of unaccepted ball-pin product | |
| CN113688817A (en) | Instrument identification method and system for automatic inspection | |
| CN103824092A (en) | Image classification method for monitoring state of electric transmission and transformation equipment on line | |
| TWI776176B (en) | Device and method for scoring hand work motion and storage medium | |
| Wang et al. | Pointer meter recognition in UAV inspection of overhead transmission lines | |
| CN113343998A (en) | Reading monitoring system and method for electric power mechanical meter, computer equipment and application | |
| CN109145752A (en) | For assessing the method, apparatus, equipment and medium of object detection and track algorithm | |
| CN110807416A (en) | Digital instrument intelligent recognition device and method suitable for mobile detection device | |
| CN109063688A (en) | LED status recognition methods based on intelligent inspection robot | |
| CN109598692A (en) | A kind of defect inspection method based on the detection of local contrast salient region | |
| CN111738259A (en) | Tower state detection method and device | |
| CN114330477B (en) | Power equipment defect detection system and method based on mixed reality equipment | |
| CN114355083A (en) | Inspection robot fault identification method and system based on artificial intelligence algorithm | |
| CN114708233A (en) | Method for measuring pig carcass thickness and related product | |
| Di et al. | Research on Real-Time Power Line Damage Detection Method Based on YOLO Algorithm | |
| CN114529493A (en) | Cable appearance defect detection and positioning method based on binocular vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |